{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QO6XCM2M7JBXDF5KEUST22EFQ5","short_pith_number":"pith:QO6XCM2M","schema_version":"1.0","canonical_sha256":"83bd71334cfa437197aa25253d688587785b579aadcf5d65bf2f3fe11da339b8","source":{"kind":"arxiv","id":"2310.07931","version":1},"attestation_state":"computed","paper":{"title":"D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Adyasha Maharana, Mohit Bansal, Prateek Yadav","submitted_at":"2023-10-11T23:01:29Z","abstract_excerpt":"Analytical theories suggest that higher-quality data can lead to lower test errors in models trained on a fixed data budget. Moreover, a model can be trained on a lower compute budget without compromising performance if a dataset can be stripped of its redundancies. Coreset selection (or data pruning) seeks to select a subset of the training data so as to maximize the performance of models trained on this subset, also referred to as coreset. There are two dominant approaches: (1) geometry-based data selection for maximizing data diversity in the coreset, and (2) functions that assign difficult"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.07931","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T23:01:29Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"a167c0c623258c835d8d1d5bbd5b66d7230e37c4af850e37855936b05b9cda5b","abstract_canon_sha256":"e25e26852daca929e9352f970f19da097c68511c9acc469d2814ed84ed9d5809"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:58.361883Z","signature_b64":"hLLbXoFmnnjBuDz/NMCyk3CwX2QAJQKKV4kJMaPQjJZhMPFmiD5BdfW5xHaqmqntu61le2Nda0W7SKWZubWrBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83bd71334cfa437197aa25253d688587785b579aadcf5d65bf2f3fe11da339b8","last_reissued_at":"2026-07-05T06:59:58.361376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:58.361376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Adyasha Maharana, Mohit Bansal, Prateek Yadav","submitted_at":"2023-10-11T23:01:29Z","abstract_excerpt":"Analytical theories suggest that higher-quality data can lead to lower test errors in models trained on a fixed data budget. Moreover, a model can be trained on a lower compute budget without compromising performance if a dataset can be stripped of its redundancies. Coreset selection (or data pruning) seeks to select a subset of the training data so as to maximize the performance of models trained on this subset, also referred to as coreset. There are two dominant approaches: (1) geometry-based data selection for maximizing data diversity in the coreset, and (2) functions that assign difficult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07931","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.07931/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.07931","created_at":"2026-07-05T06:59:58.361436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07931v1","created_at":"2026-07-05T06:59:58.361436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07931","created_at":"2026-07-05T06:59:58.361436+00:00"},{"alias_kind":"pith_short_12","alias_value":"QO6XCM2M7JBX","created_at":"2026-07-05T06:59:58.361436+00:00"},{"alias_kind":"pith_short_16","alias_value":"QO6XCM2M7JBXDF5K","created_at":"2026-07-05T06:59:58.361436+00:00"},{"alias_kind":"pith_short_8","alias_value":"QO6XCM2M","created_at":"2026-07-05T06:59:58.361436+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02830","citing_title":"Mitigating Spurious Correlations with Memorization-Guided Dataset De-Biasing","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14773","citing_title":"Beyond What to Select: A Plug-and-play Oscillatory Data-Volume Scheduling for Efficient Model Training","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26004","citing_title":"MAGIC: Multimodal Alignment & Grounding-aware Instruction Coreset for Vision-Language Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11328","citing_title":"Select Smarter, Not More: Prompt-Aware Evaluation Scheduling with Submodular Guarantees","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16979","citing_title":"DOSE: Data Selection for Multi-Modal LLMs via Off-the-Shelf Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02757","citing_title":"Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QO6XCM2M7JBXDF5KEUST22EFQ5","json":"https://pith.science/pith/QO6XCM2M7JBXDF5KEUST22EFQ5.json","graph_json":"https://pith.science/api/pith-number/QO6XCM2M7JBXDF5KEUST22EFQ5/graph.json","events_json":"https://pith.science/api/pith-number/QO6XCM2M7JBXDF5KEUST22EFQ5/events.json","paper":"https://pith.science/paper/QO6XCM2M"},"agent_actions":{"view_html":"https://pith.science/pith/QO6XCM2M7JBXDF5KEUST22EFQ5","download_json":"https://pith.science/pith/QO6XCM2M7JBXDF5KEUST22EFQ5.json","view_paper":"https://pith.science/paper/QO6XCM2M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07931&json=true","fetch_graph":"https://pith.science/api/pith-number/QO6XCM2M7JBXDF5KEUST22EFQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/QO6XCM2M7JBXDF5KEUST22EFQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QO6XCM2M7JBXDF5KEUST22EFQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QO6XCM2M7JBXDF5KEUST22EFQ5/action/storage_attestation","attest_author":"https://pith.science/pith/QO6XCM2M7JBXDF5KEUST22EFQ5/action/author_attestation","sign_citation":"https://pith.science/pith/QO6XCM2M7JBXDF5KEUST22EFQ5/action/citation_signature","submit_replication":"https://pith.science/pith/QO6XCM2M7JBXDF5KEUST22EFQ5/action/replication_record"}},"created_at":"2026-07-05T06:59:58.361436+00:00","updated_at":"2026-07-05T06:59:58.361436+00:00"}